INDEX

Explanations

locations or geographical features, particularly with the word "Ridge" in them

oai_token-act-pair · gpt-3.5-turbo

references to specific locations or geographical features, particularly a ridge

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

glomer

-0.92

alg

-0.73

ulative

-0.71

alien

-0.70

ADRA

-0.62

emort

-0.62

 laundering

-0.60

itivity

-0.60

 Chomsky

-0.60

endi

-0.60

POSITIVE LOGITS

cliffe

1.13

 Racer

1.02

leigh

1.01

 Ridge

0.99

leys

0.83

robe

0.80

phrine

0.78

tta

0.78

mallow

0.78

mma

0.78

Activations Density 0.018%

locations or geographical features, particularly with the word "Ridge" in them

references to specific locations or geographical features, particularly a ridge

No Comments

No Known Activations